Curvature-Aligned Federated Learning (CAFe): Harmonizing Loss Landscapes for Fairness Without Demographics

• URL: http://arxiv.org/abs/2404.19725v5
• Date: Tue, 08 Jul 2025 03:57:12 GMT
• Title: Curvature-Aligned Federated Learning (CAFe): Harmonizing Loss Landscapes for Fairness Without Demographics
• Authors: Shaily Roy, Harshit Sharma, Asif Salekin,
• Abstract summary: Federated Learning (FL) enables privacy-preserving collaborative training.<n>Current methods rely on sensitive attribute knowledge, which conflicts with FL's privacy principles.<n>We introduce Curvature-Aligned Federated Learning (CAFe) to achieve fairness in FL without requiring sensitive attribute knowledge.
• Score: 1.6317541379125347
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated Learning (FL) enables privacy-preserving collaborative training, making it well-suited for decentralized human-sensing applications. Ensuring fairness in FL is challenging, as current methods rely on sensitive attribute knowledge, which conflicts with FL's privacy principles. Additionally, sensitive attributes in human-sensing data may be unknown or latent. To address this, we introduce Curvature-Aligned Federated Learning (CAFe), a theoretically grounded approach that achieves fairness in FL without requiring sensitive attribute knowledge, a concept termed "Fairness without Demographics" (FWD). CAFe introduces loss-landscape curvature regularization during local training and clients' loss-landscape sharpness-aware aggregation to align curvature both within and across clients, enabling a strong balance between higher fairness and performance. CAFe is especially suitable for real-world human-sensing FL scenarios involving single or multi-user edge devices with unknown or multiple bias factors. We validated CAFe through theoretical and empirical justifications, and comprehensive evaluations using three real-world datasets and a live real-world FL deployment with a heterogeneous testbed of resource-constrained devices. Additionally, we conduct sensitivity analyses on local training data volume, client sampling, communication overhead, resource costs, and runtime performance to demonstrate its feasibility for practical FL edge device deployment.

Related papers

• FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments [4.358456799125694]
  Pervasive computing environments (e.g., for Human Activity Recognition, HAR) are characterized by resource-constrained end devices, streaming sensor data and intermittent client participation.<n>We propose FlexFed, a novel FL approach that prioritizes data retention for efficient memory use and dynamically adjusts offline training frequency.<n>We also develop a realistic HAR-based evaluation framework that simulates streaming data, dynamic distributions, imbalances and varying availability.
  arXiv  Detail & Related papers  (2025-05-19T14:23:37Z)
• Benchmarking Mutual Information-based Loss Functions in Federated Learning [2.79786165508341]
  Federated Learning (FL) has attracted considerable interest due to growing privacy regulations. This paper examines the use of Mutual Information (MI)-based loss functions to address these concerns.
  arXiv  Detail & Related papers  (2025-04-16T08:58:44Z)
• FedTilt: Towards Multi-Level Fairness-Preserving and Robust Federated Learning [12.713572267830658]
  textttFedTilt is a novel FL that can preserve multi-level fairness and be robust to outliers.<n>We show how tuning tilt values can achieve the two-level fairness and mitigate the persistent outliers.
  arXiv  Detail & Related papers  (2025-03-15T19:57:23Z)
• FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysis [39.424995330773264]
  FedPCA identifies mislabeled clients via a Gaussian Mixture Model on loss-dispersion pairs.<n>It applies fairness and robustness strategies in global aggregation and local training by adjusting client weights and selectively using reliable data.
  arXiv  Detail & Related papers  (2025-03-13T17:18:18Z)
• Feasible Learning [78.6167929413604]
  We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample. Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
  arXiv  Detail & Related papers  (2025-01-24T20:39:38Z)
• Towards Harmless Rawlsian Fairness Regardless of Demographic Prior [57.30787578956235]
  We explore the potential for achieving fairness without compromising its utility when no prior demographics are provided to the training set. We propose a simple but effective method named VFair to minimize the variance of training losses inside the optimal set of empirical losses.
  arXiv  Detail & Related papers  (2024-11-04T12:40:34Z)
• PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning [2.8304839563562436]
  Training and deploying Machine Learning models that simultaneously adhere to principles of fairness and privacy poses a significant challenge. We introduce PUFFLE, a high-level parameterised approach that can help in the exploration of the balance between utility, privacy, and fairness in FL scenarios. We prove that PUFFLE can be effective across diverse datasets, models, and data distributions, reducing the model unfairness up to 75%, with a maximum reduction in the utility of 17% in the worst-case scenario.
  arXiv  Detail & Related papers  (2024-07-21T17:22:18Z)
• FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants [41.070716405671206]
  Federated learning (FL) provides a privacy-preserving approach for collaborative training of machine learning models. It is crucial to select appropriate collaborators for each FL participant based on data complementarity. It is imperative to consider the inter-individual relationships among FL-PTs where some FL-PTs engage in competition.
  arXiv  Detail & Related papers  (2023-12-18T17:53:01Z)
• Multi-dimensional Fair Federated Learning [25.07463977553212]
  Federated learning (FL) has emerged as a promising collaborative and secure paradigm for training a model from decentralized data. Group fairness and client fairness are two dimensions of fairness that are important for FL. We propose a method, called mFairFL, to achieve group fairness and client fairness simultaneously.
  arXiv  Detail & Related papers  (2023-12-09T11:37:30Z)
• Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification [51.04894019092156]
  Federated learning (FL) has been recognized as a rapidly growing area, where the model is trained over clients under the FL orchestration (PS) In this paper, we propose a novel primal sparification algorithm for and guarantee non-smooth FL problems. Its unique insightful properties and its analyses are also presented.
  arXiv  Detail & Related papers  (2023-10-30T14:15:47Z)
• Learning for Counterfactual Fairness from Observational Data [62.43249746968616]
  Fairness-aware machine learning aims to eliminate biases of learning models against certain subgroups described by certain protected (sensitive) attributes such as race, gender, and age. A prerequisite for existing methods to achieve counterfactual fairness is the prior human knowledge of the causal model for the data. In this work, we address the problem of counterfactually fair prediction from observational data without given causal models by proposing a novel framework CLAIRE.
  arXiv  Detail & Related papers  (2023-07-17T04:08:29Z)
• Fairness-aware Federated Minimax Optimization with Convergence Guarantee [10.727328530242461]
  Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. The lack of freedom in managing user data can lead to group fairness issues, where models are biased towards sensitive factors such as race or gender. This paper proposes a novel algorithm, fair federated averaging with augmented Lagrangian method (FFALM), designed explicitly to address group fairness issues in FL.
  arXiv  Detail & Related papers  (2023-07-10T08:45:58Z)
• FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning [102.92349569788028]
  We propose a fair vertical federated learning framework (FairVFL) to improve the fairness of VFL models. The core idea of FairVFL is to learn unified and fair representations of samples based on the decentralized feature fields in a privacy-preserving way. For protecting user privacy, we propose a contrastive adversarial learning method to remove private information from the unified representation in server.
  arXiv  Detail & Related papers  (2022-06-07T11:43:32Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [61.488646649045215]
  Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
  arXiv  Detail & Related papers  (2021-11-28T19:03:39Z)
• Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning [98.05061014090913]
  Federated learning (FL) emerges as a popular distributed learning schema that learns from a set of participating users without requiring raw data to be shared. adversarial training (AT) provides a sound solution for centralized learning, extending its usage for FL users has imposed significant challenges. We show that existing FL techniques cannot effectively propagate adversarial robustness among non-iid users. We propose a simple yet effective propagation approach that transfers robustness through carefully designed batch-normalization statistics.
  arXiv  Detail & Related papers  (2021-06-18T15:52:33Z)
• Private Cross-Silo Federated Learning for Extracting Vaccine Adverse Event Mentions [0.7349727826230862]
  Federated Learning (FL) is a goto distributed training paradigm for users to jointly train a global model without physically sharing their data. We present a comprehensive empirical analysis of various dimensions of benefits gained with FL based training. We show that local DP can severely cripple the global model's prediction accuracy, thus dis-incentivizing users from participating in the federation.
  arXiv  Detail & Related papers  (2021-03-12T19:20:33Z)
• Mitigating Bias in Federated Learning [9.295028968787351]
  In this paper, we discuss causes of bias in federated learning (FL) We propose three pre-processing and in-processing methods to mitigate bias, without compromising data privacy. We conduct experiments over several data distributions to analyze their effects on model performance, fairness metrics, and bias learning patterns.
  arXiv  Detail & Related papers  (2020-12-04T08:04:12Z)
• A Principled Approach to Data Valuation for Federated Learning [73.19984041333599]
  Federated learning (FL) is a popular technique to train machine learning (ML) models on decentralized data sources. The Shapley value (SV) defines a unique payoff scheme that satisfies many desiderata for a data value notion. This paper proposes a variant of the SV amenable to FL, which we call the federated Shapley value.
  arXiv  Detail & Related papers  (2020-09-14T04:37:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.